Jim Grosbach 4070037e3c X86: restrict combine to when type sizes are safe. ... The folding of unary operations through a vector compare and mask operation is only safe if the unary operation result is of the same size as its input. For example, it's not safe for [su]itofp from v4i32 to v4f64. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@213799 91177308-0d34-0410-b5e6-96231b3b80d8		2014-07-23 20:41:38 +00:00
..
Analysis	Make use of the align parameter attribute for all pointer arguments	2014-07-22 16:58:55 +00:00
AsmParser	AsmParser: remove deprecated LLIR support	2014-07-23 18:09:31 +00:00
Bitcode	Add a dereferenceable attribute	2014-07-18 15:51:28 +00:00
CodeGen	DAG: fp->int conversion for non-splat constants.	2014-07-23 20:41:31 +00:00
DebugInfo
ExecutionEngine	ExecutionEngine: remove a stray semicolon	2014-07-23 18:09:28 +00:00
IR	Rename metadata llvm.loop.vectorize.unroll to llvm.loop.vectorize.interleave.	2014-07-21 23:11:03 +00:00
IRReader
LineEditor
Linker
LTO	AArch64: remove arm64 triple enumerator.	2014-07-23 12:32:47 +00:00
MC	AArch64: remove arm64 triple enumerator.	2014-07-23 12:32:47 +00:00
Object	AArch64: remove arm64 triple enumerator.	2014-07-23 12:32:47 +00:00
Option
ProfileData
Support	AArch64: remove "arm64_be" support in favour of "aarch64_be".	2014-07-23 12:58:11 +00:00
TableGen	[TableGen] Allow shift operators to take bits<n>	2014-07-17 17:04:27 +00:00
Target	X86: restrict combine to when type sizes are safe.	2014-07-23 20:41:38 +00:00
Transforms	Do not add unroll disable metadata after unrolling pass for loops with #pragma clang loop unroll(full).	2014-07-23 20:05:44 +00:00
CMakeLists.txt
LLVMBuild.txt
Makefile